如果用特殊字符（例如 R 中的“+”符号）分隔，则为数据框中的项目创建新行

Question

我有一个文本文件中的数据，其中包含多个列，我想以不丢失任何信息的方式处理数据，有些列包含两个或多个用特殊字符分隔的信息，例如“+”加号，我想把这些组合信息放在同一列的不同行中，例如我在下面粘贴数据
我的数据框如下所示

df <- data.frame(G1=c("GH13_22+CBM4",  "GH109+PL7+GH9","GT57", "AA3","",""),
                 G2=c("GH13_22","","GT57+GH15","AA3", "GT41","PL+PL2"),
                 G3=c("GH13", "GH1O9","", "CBM34+GH13+CBM48", "GT41","GH16+CBM4+CBM54+CBM32"))

             G1        G2                    G3
1  GH13_22+CBM4   GH13_22                  GH13
2 GH109+PL7+GH9                           GH1O9
3          GT57 GT57+GH15
4           AA3       AA3      CBM34+GH13+CBM48
5                    GT41                  GT41
6                  PL+PL2 GH16+CBM4+CBM54+CBM32

预期结果应该看起来像

df2 <- data.frame(G1=c("GH13_22","CBM4",  "GH109","PL7","GH9","GT57", "AA3","","","",""),
                  G2=c("GH13_22","","GT57","GH15","AA3", "GT41","PL","PL2","","",""),
                  G3=c("GH13", "GH1O9","", "CBM34","GH13","CBM48", "GT41","GH16","CBM4","CBM54","CBM32")) 

        G1      G2    G3
1  GH13_22 GH13_22  GH13
2     CBM4         GH1O9
3    GH109    GT57
4      PL7    GH15 CBM34
5      GH9     AA3  GH13
6     GT57    GT41 CBM48
7      AA3      PL  GT41
8              PL2  GH16
9                   CBM4
10                 CBM54
11                 CBM32

感谢任何帮助 谢谢

Answer 1

另一个选项，灵感来自这篇文章中的@Peter M

library(tidyverse)
library(stringr)

# finds which vector is the longest and pads the other vectors accordingly
makePaddedDataFrame <- function(l){
  maxlen <- max(sapply(l,length))
  data.frame(lapply(l,\(x) x[1:maxlen])) # pads vectors with na
}

df %>% 
  mutate(across(.fns = function(x) str_split(x, pattern="\\+"))) %>% 
  lapply(function(x) do.call(c, x)) %>% 
  makePaddedDataFrame %>% 
  replace(is.na(.), " ") # if you want empty strings instead of na

        G1      G2    G3
1  GH13_22 GH13_22  GH13
2     CBM4         GH1O9
3    GH109    GT57      
4      PL7    GH15 CBM34
5      GH9     AA3  GH13
6     GT57    GT41 CBM48
7      AA3      PL  GT41
8              PL2  GH16
9                   CBM4
10                 CBM54
11                 CBM32

Answer 2

separate_rows()

已被

separate_longer_delim()

取代，因为它具有与其他独立函数更一致的 API。被取代的功能不会消失，但只会收到关键错误修复。 https://tidyr.tidyverse.org/reference/separate_rows.html

1. 我们带来长格式的数据
2. 使用

   na_if

   从

   dplyr

用NA替换空白
3. 通过这行代码

   summarise(cur_data()[seq(max(id)), ]) 

   我们将每个组扩展到id的最大值。
4. 最后我们将准备好的数据框转回：

library(dplyr)
library(tidyr)

df %>% 
  pivot_longer(everything()) %>% 
  separate_longer_delim(value, "+") %>% 
  mutate(value = na_if(value, "")) %>% 
  group_by(name) %>% 
  mutate(id = row_number()) %>% 
  summarise(cur_data()[seq(max(id)), ]) %>% 
  pivot_wider(names_from = name, values_from = value) 

      id G1      G2      G3   
   <int> <chr>   <chr>   <chr>
 1     1 GH13_22 GH13_22 GH13 
 2     2 CBM4    NA      GH1O9
 3     3 GH109   GT57    NA   
 4     4 PL7     GH15    CBM34
 5     5 GH9     AA3     GH13 
 6     6 GT57    GT41    CBM48
 7     7 AA3     PL      GT41 
 8     8 NA      PL2     GH16 
 9     9 NA      NA      CBM4 
10    10 NA      NA      CBM54
11    11 NA      NA      CBM32

Answer 3

一个

base

解决方案：

split <- lapply(df, \(x) unlist(strsplit(replace(x, x == '', NA_character_), '\\+')))
as.data.frame(lapply(split, `[`, 1:max(lengths(split))))

        G1      G2    G3
1  GH13_22 GH13_22  GH13
2     CBM4    <NA> GH1O9
3    GH109    GT57  <NA>
4      PL7    GH15 CBM34
5      GH9     AA3  GH13
6     GT57    GT41 CBM48
7      AA3      PL  GT41
8     <NA>     PL2  GH16
9     <NA>    <NA>  CBM4
10    <NA>    <NA> CBM54
11    <NA>    <NA> CBM32